Introduction to the Special Issue on Advanced Graph Mining on the Web: Theory, Algorithms, and Applications: Part 1

We are delighted to present this special issue on Advanced Graph Mining on the Web: Theory, Algorithms, and Applications. Graph mining plays an important role in data mining on the Web. It can take full advantage of the growing and easily accessible big data resources on the Web, such as rich semantic information in social media and complex associations between users in online social networks, which is crucial for the development of systems and applications such as event detection, social bot detection, and intelligent recommendation. However, extracting valuable and representative information from Web graph data is still a great challenge and requires research and development on advanced techniques. The purpose of this special issue is to provide a forum for researchers and practitioners to present their latest research findings and engineering experiences in the theoretical foundations, empirical studies, and novel applications of Graph Mining. This special issue consists of two parts. In Part 1, the guest editors selected 10 contributions that cover varying topics within this theme, ranging from reinforced and self-supervised GNN architecture search framework to the streaming growth algorithm of bipartite graphs.

Yang et al. in “RoSGAS: Adaptive Social Bot Detection with Reinforced Self-supervised GNN Architecture Search” proposed a novel Reinforced and Self-supervised GNN Architecture Search framework named RoSGAS, which gains improvement in terms of accuracy, training efficiency, and stability. And has better generalization when handling unseen samples.

Du et al. in “Niffler: Real-time Device-level Anomalies Detection in Smart Home” proposed a novel notion—a correlated graph, and with the aid of that, they developed a system to detect misbehaving devices without modifying the existing system, which is crucial for the device-level security in the smart home system. And then they further proposed a linkage path model and a sensitivity ranking method to assist in detecting the abnormalities.

Sun et al. in “GroupAligner: A Deep Reinforcement Learning with Domain Adaptation for Social Group Alignment” presented a novel GroupAligner, a deep reinforcement learning with domain adaptation for social group alignment, which solves the problems of feature inconsistency across different social networks and group discovery within a social network in social group alignment.

Zhu et al. in “AMulti-task Graph Neural Network with Variational Graph Auto-encoders for Session-based Travel Packages Recommendation” proposed a novel session-based model named STR-VGAE, which provides robust attributes’ representations and takes the effects of historical sessions for the current session into consideration. The model obtained promising results in the session-based recommendation, and can fill subtasks of the travel packages recommendation and variational graph auto-encoders simultaneously.

Usman Ahmed et al. in “Graph Attention Network for Text Classification and Detection of Mental Disorder” used Graph Attention Networks to solve the problems associated with text classification of depression in order to identify depressive symptoms through the language used in individuals’ personal expressions. Rather than requiring expensive matrix operations such as similarity or knowledge of network architecture, this study implicitly assigns weights to each node in a neighborhood.

Li et al. in “Type Information Utilized Event Detection via Multi-channel GNNs in Electrical Power Systems” proposed a Multi-channel graph neural network utilizing Type information for Event Detection in power systems, named MC-TED, leveraging a semantic channel and a topological channel to enrich information interaction from short texts. Specifically, the semantic channel refines textual representations with semantic similarity, and a type-learning mechanism is designed for updating the representations of both the word type and relation type in the topological channel.

Wang et al. in “Heterogeneous Graph Transformer for Meta-structure Learning with Application in Text Classification” proposed a novel approach called HeGTM to automatically extract essential meta-structures from heterogeneous graphs. And the discovered meta-structures can capture more prosperous relations between different types of nodes that can help the model to learn representations.

Gong et al. in “Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks” proposed a novel Heterogeneous Information Networks based Concept Recommender with Reinforcement Learning incorporated for concept recommendation in MOOCs. What is more, they identified and investigated the problem of concept recommendation, which is a more fine-grained recommendation task than course recommendation in MOOCs.

Shang et al. in “Constructing Spatio-temporal Graphs for Face Forgery Detection” proposed to construct spatial-temporal graphs for fake videos to capture the spatial inconsistency and the temporal incoherence simultaneously. And a novel forgery detector named Spatio-temporal Graph Network was proposed to model the spatial-temporal relationship among the graph nodes, which achieves state-of-the-art performances in face forgery detection.

Sheshbolouki et al. in “sGrow: Explaining the Scale-Invariant Strength Assortativity of Streaming Butterflies” provided the graph-theoretic explanation of a phenomenon called “scale-invariant strength assortativity of streaming butterflies” in streaming settings of bipartite graphs. And then introduced a set of micro-mechanics in the body of a streaming growth algorithm named sGrow to pinpoint the generative origins.

The guest editors believe the articles appearing in this issue represent the frontiers of current topics in the field of Graph Mining and hope these articles will stimulate further development in this area. The editors sincerely appreciate the authors and reviewers’ tremendous contributions to this special issue.

We hope you enjoy this special issue and take some inspiration from it for your own future research.